Generating fit-for-purpose CAE models from complex CAD assemblies is time consuming and error-prone. Tedious tasks include identifying and isolating the components of interest, removing duplicate components, and correcting inconsistent component interfaces. In this paper a new approach to help engineers identify similar features and analyse the consistency of CAD assembly models is proposed. The method utilises a tensor factorisation technique developed for relational machine learning and applies it to B-Rep topological and geometrical relations. The model considers globally all the input relations to identify which entities in the assembly are similar (within a user-defined threshold) to a selected input entity. It is shown that a hierarchical clustering method can group entities, based on the similarities of their attributes and relationships with adjacent components. It is shown how some unsuspected CAD modelling errors show up as features which should be similar, but which are not. It is demonstrated how the technique can be used to support the, currently highly manual, task of decomposing a volume representing an internal fluid network into sub-volumes and features of significance.